Master Thesis - Department of Computer Science
Master Thesis - Department of Computer Science
Master Thesis - Department of Computer Science
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
(a) cn(p) = 2 (b) cn(p) = 1 (c) cn(p) = 3<br />
Figure A.15: (a)Intra-ridge pixel; (b) Termination minutia; (c) Bifurcation minutia.<br />
• is an intermediate ridge point, if cn(p) = 2;<br />
• corresponds to a termination minutia, if cn(p) = 3;<br />
• defines a more complex minutia (bifurcation, crossover, etc.), if cn(p) ≥ 3<br />
For each extracted minutiae point, the following information is recorded:<br />
• x and y coordinates,<br />
• orientation, α, <strong>of</strong> the associated ridge segment, and<br />
• type <strong>of</strong> the minutiae (ridge ending or bifurcation).<br />
In the second stage, there are 3-4 levels <strong>of</strong> elimination: nearby features, L-shaped<br />
false bifurcations, boundary effects and spike elimination.<br />
• Ridge break elimination: Two end points with the same orientation and<br />
within a distance threshold T1 are eliminated.<br />
• Spike elimination: An end point which is connected to a bifurcation point<br />
and is also within a distance threshold T2 is eliminated.<br />
• Boundary effects: The minutiae detected within a specified border <strong>of</strong> the<br />
boundary <strong>of</strong> the foreground areas are deleted.<br />
The post-processing stage eliminates spurious feature points based on the structural<br />
and spatial relationships <strong>of</strong> the minutiae. In Fig. A.16, the minutiae features after<br />
post-processing, for two input fingerprint images are shown. Bifurcations are marked<br />
138